Peyman Moghadam
Commonwealth Scientific and Industrial Research Organisation
CSIRO researcher advancing robot place recognition across radar and vision, with two 2026 last-author arXiv papers
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-02) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
Not yet scored: the snapshot lacks sufficient publication-volume data (e.g. total paper and citation counts) to compute an output score. This axis would measure the breadth and regularity of research output across venues and years.
Impact—
Not yet scored: citation signals are unavailable in this snapshot, so field influence cannot be quantified. This axis would measure citation counts, citation velocity, and uptake of his radar and visual place recognition methods by other groups.
Focus0/100
The radar assigns focus a score of 0, reflecting a field distribution split exactly 50/50 between two bibliographic labels — robotics/computer vision (radar place recognition) and computer vision/robotics (visual place recognition). Read substantively, both halves target the same underlying problem of place recognition on different sensors, so topical breadth is narrow even though no single field label dominates; only two reviewed papers inform this estimate.
Collaboration41/100
Collaboration scores 41, built on 7 distinct coauthors recorded in the snapshot. The recurring circle — Saimunur Rahman, Sagun Singh Shrestha, Abdelwahed Khamis, Walter Nedov, Kavindie Katuwandeniya, David Hall and Kaushik Roy — points to a stable, CSIRO-anchored team. On both catalogued papers he occupies the last author position without corresponding authorship, consistent with a supervisory role rather than a large distributed network.
Activity—
Not yet scored: the snapshot does not provide per-year publication counts, so research tempo cannot be computed. This axis would measure recent publication frequency and continuity — useful given that both catalogued papers appeared in 2026.
Reproducibility55/100
Reproducibility scores 55, the mean across 2 reviewed papers (reproMean 55, reproPapers 2), each rated medium readiness. Both papers report concrete benchmark numbers — 91.3 vs 87.7 R@1@5m on MulRan and 61.41→66.37 inter-sequence R@1 on WildCross — and the visual work is described as well ablated; however, code availability is not noted in the reviews, and the radar paper leaves newer SOTA baselines untested.
Research summary
Peyman Moghadam is a researcher at the Commonwealth Scientific and Industrial Research Organisation (CSIRO) whose recent work concentrates on place recognition — a robot's ability to recognise where it has been before — across two complementary sensing modalities. The Evolve catalog records two 2026 arXiv papers on which he appears as last author: an automotive mmWave spinning-radar place recognition method built on spatially gated feature-correlation (covariance pooling) representations, and a geometry-conditioned visual place recognition approach that injects geometric-foundation-model depth into vision-foundation-model tokens. The radar paper reports 91.3 vs 87.7 Recall@1 at 5 m against RadarLoc on MulRan and transfers zero-shot to HeRCULES; the visual paper lifts WildCross inter-sequence Recall@1 from 61.41 to 66.37. His bibliographic field profile splits evenly (0.5/0.5) between radar-based and vision-based place recognition — two labels that target the same problem on different sensors — and he works within a compact circle of 7 distinct coauthors. Evolve scored reproducibility at 55 across both papers (medium readiness each), while the output, impact and activity axes await sufficient data. Both reviews note that stronger or newer baselines remain untested, so the headline gains should be read as solid but not yet fully benchmarked.
Collaboration pattern
The snapshot records 7 distinct coauthors, and collaboration scores 41. The recurring circle — Saimunur Rahman, Sagun Singh Shrestha, Abdelwahed Khamis, Walter Nedov, Kavindie Katuwandeniya, David Hall and Kaushik Roy — points to a stable, CSIRO-anchored team rather than a wide external network. On both catalogued 2026 papers Moghadam occupies the last author position without corresponding authorship, a pattern consistent with senior supervision of hands-on first authors.
Research keywords
Highlights
Spinning-radar place recognition edges past RadarLoc on MulRan
Depth-distilled geometry conditioning lifts visual place recognition
Timeline
- 2026Last-author arXiv paper on automotive mmWave spinning radar place recognition with spatially gated feature-correlation representation.
- 2026Last-author arXiv paper on geometry-conditioned visual place recognition in natural environments (DAD).
- 2026Both 2026 outputs land in radar and visual place recognition, splitting the catalogued field profile 50/50 across the two modalities.
Papers in the Evolve catalog
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- Bibliometric scores derive from the platform's bibliometric snapshot only; the output, impact and activity axes lack sufficient data and are unscored.
- Profile evidence rests on just 2 Evolve-reviewed papers (both 2026 arXiv preprints), so career-level claims are out of scope.
- No ORCID or country is linked in the snapshot; identity is name-resolved from public bibliographic data.
- Reproducibility and focus scores reflect Evolve's assessment of the two reviewed papers only.